TRIGGER WORD DETECTION WITH MULTIPLE DIGITAL ASSISTANTS

    公开(公告)号:US20240177712A1

    公开(公告)日:2024-05-30

    申请号:US18431516

    申请日:2024-02-02

    Applicant: Roku, Inc.

    Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.

    Trigger Word Detection With Multiple Digital Assistants

    公开(公告)号:US20190251960A1

    公开(公告)日:2019-08-15

    申请号:US15895047

    申请日:2018-02-13

    Applicant: Roku, Inc.

    Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.

    TRIGGER WORD DETECTION WITH MULTIPLE DIGITAL ASSISTANTS

    公开(公告)号:US20230252992A1

    公开(公告)日:2023-08-10

    申请号:US18303336

    申请日:2023-04-19

    Applicant: Roku, Inc.

    Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.

    Trigger Word Detection with Multiple Digital Assistants

    公开(公告)号:US20210383807A1

    公开(公告)日:2021-12-09

    申请号:US17412527

    申请日:2021-08-26

    Applicant: Roku, Inc.

    Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.

    Generating Playback Configurations Based on Aggregated Crowd-Sourced Statistics

    公开(公告)号:US20200313993A1

    公开(公告)日:2020-10-01

    申请号:US16725075

    申请日:2019-12-23

    Applicant: Roku, Inc.

    Abstract: A processor and a memory connected to the processor store instructions executed by the processor to collect playback statistics including audio attributes or video attributes associated with playback of specified content from multiple devices, aggregate the playback statistics, and establish a playback configuration for the specified content based on the playback statistics. The specified device here may be a type of content player or server.

Patent Agency Ranking